Obviously AI also has an advanced analytics tab which gives you a Decision Tree graph that shows the various course of action taken to get to the outcome.
The Decision Tree consists of nodes and branches. At each node each feature/column is split based on its importance to make specific data points follow a certain course for making predictions.
A Decision Tree essentially consists of three elements.
- Root Node: It is the first node or the Parent node that begins the Tree Graph. The root node is the most important feature/column that best splits the Data.
- Intermediate Nodes: This represents the remaining columns or features which are important in predicting the output.
- Leaf Node: This is the last/final node which contains the prediction value.
Obviously AI allows you to download the Decision Tree to your computer.
- Navigate to the Advanced Analytics tab on the Prediction Report.
- Finally, click on the Download button on the right to download the Decision Tree
- Here Contract = Month-to-month represents the Root Node.
- Monthly Charges, Online security = No, Total Charges represents the Intermediate Nodes.
- Class = Yes and Class = No represents the Leaf Node, which are the predictions.